Your question is Rapid Scaling With Cost Controls. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How would you plan for capacity in a system that needs to scale rapidly while managing costs?
Discuss the information you would gather, how you would estimate demand and infrastructure requirements, and how you would balance latency, availability, and spend. Address online and batch inference, autoscaling, capacity headroom, load testing, cost monitoring, and failure handling.
